SShogo Bench

Beam 1.0 501B A23B

Sparse mixture-of-experts reasoning model with 23B active parameters for coding and agentic workflows

Shogo Agent Index

Unranked

Not ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.

Agentic coding
—
estimated
Long-horizon autonomy
—
estimated
Knowledge-work agents
—
estimated
Computer use
—
estimated
Security & context learning
—
estimated

Price

Input
Free/M
Output
Free/M
Cache read
Free/M
3:1 blend
Free/M
Agent-effective
Free/M

Cheapest host for agents: CoreWeave at $0.12/M.

Agent-effective = 20 input tokens per output token, 85% cache hits. Why.

Agentic benchmarks

BenchmarkScoreNormalisedIndex weightHarness / source
SWE-bench Verifiedest.8%—
Terminal-Bench 2.0est.8%—
DeepSWEest.6%—
FrontierSWEest.5%—
CursorBenchest.4%—
GSO-Benchest.4%—
METR Time Horizonsest.10%—
Vending-Bench 2est.6%—
PostTrainBenchest.4%—
APEX-Agentsest.8%—
GDPvalest.7%—
Remote Labor Indexest.5%—
DeepResearch Benchest.5%—
OSWorld 2.0est.6%—
OSWorldest.4%—
Cybenchest.5%—
CL-benchest.5%—

API hosts

Live prices and uptime for every host serving Beam 1.0 501B A23B via OpenRouter.

HostInputOutputCache readAgent $/MUptime 24hQuant
CoreWeave$0.30$1.00$0.040$0.1297.2%nvfp4
Nebius$0.25$1.00$0.050$0.1298.9%fp4
BaseTen$0.40$1.20$0.040$0.15100.0%fp4
DigitalOcean$0.40$1.20$0.040$0.1599.5%—
Together$0.40$1.20$0.040$0.1599.2%—